MIME-Version: 1.0
In-Reply-To: <20150220010506.GA10837@node.dhcp.inet.fi>
References: <54E5DFED.9050700@citrix.com>
	<20150220010506.GA10837@node.dhcp.inet.fi>
Date: Thu, 19 Feb 2015 17:49:07 -0800
Message-ID: <CA+55aFw-E=vRRq=jKMCJQn=qj6FZ0h8d6DZf2w3m44dmE_T6CA@mail.gmail.com>
Subject: Re: NUMA_BALANCING and Xen PV guest regression in 3.20-rc0
From: Linus Torvalds <torvalds@linux-foundation.org>
To: "Kirill A. Shutemov" <kirill@shutemov.name>
Cc: David Vrabel <david.vrabel@citrix.com>, Mel Gorman <mgorman@suse.de>,
        "linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
        "Xen-devel@lists.xen.org" <Xen-devel@lists.xen.org>
Content-Type: text/plain; charset=UTF-8
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 1084
Lines: 25

On Thu, Feb 19, 2015 at 5:05 PM, Kirill A. Shutemov
<kirill@shutemov.name> wrote:
>
> I'm feeling I miss very basic background on how Xen works, but why does it
> set _PAGE_GLOBAL on userspace entries? It sounds strange to me.

It is definitely strange. I'm guessing that it's some ancient Xen hack
for the early Intel virtualization that used to have absolutely
horrendous vmenter/exit costs, including very much the TLB overhead. \

These days, Intel has address space identifiers, and doesn't flush the
whole TLB on VM entry/exit, so it's probably pointless to play games
with the global bit.

I get the feeling that a lot of Xen stuff is that kind of "legacy
hacks" that should just be cleaned up, but nobody has the energy or
the interest.  There was the whole odd crazy SHARED_KERNEL_PMD hackery
too.

                         Linus
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/